Merge pull request #8373 from jbradish/master

ENH: Added file path existence check for read_hdf

Author: jreback

doc/source/v0.15.0.txt

@@ -262,6 +262,8 @@ API changes
 
 - ``Series.to_csv()`` now returns a string when ``path=None``, matching the behaviour of ``DataFrame.to_csv()`` (:issue:`8215`).
 
+-``read_hdf`` now raises IOError properly when a file that doesn't exist is passed in. Previously, a new, empty file was created, read and stored in an HDFStore object (:issue `7715`).
+
 .. _whatsnew_0150.index_set_ops:
 
 - The Index set operations ``+`` and ``-`` were deprecated in order to provide these for numeric type operations on certain index types. ``+`` can be replace by ``.union()`` or ``|``, and ``-`` by ``.difference()``. Further the method name ``Index.diff()`` is deprecated and can be replaced by ``Index.difference()`` (:issue:`8226`)

pandas/io/pytables.py

@@ -332,6 +332,16 @@ def read_hdf(path_or_buf, key, **kwargs):
         key, auto_close=auto_close, **kwargs)
 
     if isinstance(path_or_buf, string_types):
+        
+        try:
+            exists = os.path.exists(path_or_buf)
+
+        #if filepath is too long
+        except (TypeError,ValueError):
+            exists = False
+
+        if not exists:
+            raise IOError('File %s does not exist' % path_or_buf)
 
         # can't auto open/close if we are using an iterator
         # so delegate to the iterator

pandas/io/tests/test_pytables.py

@@ -288,6 +288,10 @@ def test_api(self):
             self.assertRaises(TypeError, df.to_hdf, path,'df',append=True,format='foo')
             self.assertRaises(TypeError, df.to_hdf, path,'df',append=False,format='bar')
 
+        #File path doesn't exist
+        path = ""
+        self.assertRaises(IOError, read_hdf, path, 'df') 
+
     def test_api_default_format(self):
 
         # default_format option